EUVIMEDEUVIMED entdecken
Crossref

Reactive Neural Network Potential Developed for Asphalt Aging Systems Through Active Learning and Enhanced Sampling

Zhengwu Long iD, Lingyun You iD

Journal of Chemical Information and Modeling · 23.02.2026 · 66 (4) · 2177-2198

DOI: 10.1021/acs.jcim.5c03194 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 09.02.2026. Verfasst von Zhengwu Long und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China. Hauptthemen laut MEDLINE: Hydrocarbons, Neural Networks, Computer, Machine Learning. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Wuhan Key Research and Development Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The atomic-scale mechanisms of asphalt oxidative aging remain poorly understood due to the chemical complexity of asphalt and limitations of conventional methods. Herein, we develop a reactive neural network potential (NNP) for asphalt-oxygen systems via active learning combined with enhanced sampling (well-tempered metadynamics). The NNP achieves quantum-mechanical accuracy while enabling large-scale molecular dynamics simulations. Coupled with multimodal experimental characterization, we uncover a sequential "dehydrogenation-oxidation-crosslinking" reaction network during aging, initiated by thiophene sulfur oxidation and followed by hydrogen abstraction, aromatization, and carbonyl formation. Temperature modulates the reaction landscape, shifting the preference from carbonylation-aromatization at low temperature to hydroxylation-aromatization at high temperature. We identify six parallel pathways with sulfoxide and carbonyl channels being dominant. Free energy analysis reveals that aging proceeds via successive polarization of C-H, O-H, C-O, and S-O bonds with energy barriers significantly lower than C-C cleavage. This work establishes a machine learning-accelerated computational framework for asphalt aging and provides guidance for designing durable pavement materials.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HydrocarbonsNeural Networks, ComputerMachine LearningMolecular Dynamics SimulationOxidation-ReductionThermodynamicsTemperatureOxygen

Substanzen

HydrocarbonsasphaltOxygen

Autor:innen und Institutionen

  • School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China.
  • National Center of Technology Innovation for Digital Construction, Huazhong University of Science and Technology, Wuhan 430074, China.

ORCID-Profile: Zhengwu Long, Lingyun You

Förderung

  • National Key Research and Development Program of China
  • Wuhan Key Research and Development Program

Zitieren

APA

Long, Z., & You, L. (2026). Reactive Neural Network Potential Developed for Asphalt Aging Systems Through Active Learning and Enhanced Sampling. Journal of Chemical Information and Modeling, 66(4), 2177-2198. https://doi.org/10.1021/acs.jcim.5c03194

Vancouver

Long Z, You L. Reactive Neural Network Potential Developed for Asphalt Aging Systems Through Active Learning and Enhanced Sampling. Journal of Chemical Information and Modeling. 2026;66(4):2177-2198. doi:10.1021/acs.jcim.5c03194

BibTeX
@article{Long2026,
  author = {Long, Zhengwu and You, Lingyun},
  title = {Reactive Neural Network Potential Developed for Asphalt Aging Systems Through Active Learning and Enhanced Sampling},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {4},
  pages = {2177--2198},
  doi = {10.1021/acs.jcim.5c03194}
}
Kostenlos starten →